--- title: "Tools: agent routing, context and skill selection" type: community source_tier: community tags: [community, tools, routing, coding-agents, context] created: 2026-09-25 updated: 2026-09-25 confidence: medium sources: - raw/x-repos/konstantinosbotonakis__codex-context-diet.md - raw/x-repos/compozy__yoshi.md - raw/x-repos/instructa__switchloom.md - raw/x-repos/Kelbie__hunch.md - raw/x-repos/altryne__jevify.md - raw/x-repos/karanb192__jev-architect.md - raw/x-repos/24601__Augustus.md - raw/x-repos/sumleo__prompt2jev.md - raw/x-repos/promptgtm-shared__clay-jev-people-ranker.md - raw/x-repos/Dicklesworthstone__skillranker.md - raw/x-repos/BillionsBobby__JevRouter.md - raw/x-repos/DevMortimer__pi-typesafe.md - raw/x-repos/shitianfang__jev-use.md - raw/x-repos/shitianfang__jev-use__bench-results.md - raw/x-repos/HorusJiang__dsh-jev-tools.md - raw/x-repos/HorusJiang__dsh-jev-tools__readme-en.md - raw/x-repos/xinyao27__jevonian.md - raw/x-repos/xinyao27__jevonian__docs-brain.md - raw/x-repos/DECRUX9812__typesafe-skill-router.md - raw/x-repos/sugarforever__yummy-pi-extensions.md - raw/x-repos/sugarforever__yummy-pi-extensions__pi-jev-router-readme.md - raw/x-repos/jsk4581__jev-blindspot.md - raw/x-repos/vinilana__jev-gateway-bench.md - raw/x-repos/NiazMorshed2007__jcr.md - raw/x-repos/vinilana__jev-gateway.md - raw/x-repos/higress-group__HiRoute.md - raw/x-repos/higress-group__HiRoute__decision-extensions-extensions-jev-decider-readme.md - raw/x-repos/fidecastro__jevify.md - docs/sweep/2026-09-25-mrjev/parta.md - docs/sweep/2026-09-25-mrjev/partc.md jev_version: "jev-1.13.0" summary: "Community Jev tools that steer coding agents rather than guard them: model, tool and skill routers, session and context pruning, wake gates, and skills that design Jev decisions." --- # Tools: agent routing, context and skill selection > **TL;DR** Plugins, hooks, proxies and skills that use Jev to pick a model, a tool, a skill or a session, or to cut context, for Claude Code, Codex, Pi, Hermes and DeepSeek Harness. **Unaudited community code**; several authors measured **no saving or a slowdown**, so read the Note column before adopting one. Split from [[ideas/tools-and-integrations]] on 2026-09-25 (nothing dropped); safety gates are on [[ideas/tools-guardrails]]. Pattern IDs: [[ideas/patterns]] (P02 model routing, P07 context, P08 skill and tool selection: [[ideas/patterns-agents]]). Licence MIT unless stated. Numbers: the author's. "Our check" = our 2026-09-25 source and registry vetting (docs/sweep/2026-09-25-mrjev/partc.md), not a raw capture. Proxies that sit in front of your agent (jev-gateway, Jevonian, Yoshi) see every request; local decision services (jev-gateway's `/router/decide`, HiRoute's jev-decider) spend your key for any local caller. ## Routers, context tools and skill selectors | Tool | Does | Install | ★ · push | Note | |---|---|---|---|---| | [typesafe-skill-router](https://github.com/DECRUX9812/typesafe-skill-router) (Ritesh Patel) | Hermes hook before the model call: wide chunked Choice with `none_of_these`, gate Nouls, then a shortlist; silent on disagreement; lists what it sends | `hermes plugins install typesafe-skill-router` (opt-in, off by default) | 14 · 2026-09-21 | port of TypeSafe's skill-suggestion cookbook ([[cookbooks/skill-suggestion]]). Author: ~0.6–1.2 s, ~$0.001 per turn (292 skills); second check p50 1.93 s, max 8.56 s; `fits` ~0.14 lower in Spanish; one miss and one off-target in the first live turns. "Budget for output tokens" **contradicts docs** (output is free, [[reference/models-and-pricing]]). P08 | | [pi-jev-router](https://github.com/sugarforever/yummy-pi-extensions) (sugarforever) | Pi: four questions (`route`, `on_topic`, `needs_history`, `one_off`) decide continue, fork or new session before a prompt enters | `pi install npm:@sugarforever/pi-jev-router` | 14 · 2026-09-23 | ~45% of prompts skip Jev; any error means continue. Author: ~0.5 s, ~1.4k input tokens, ~$0.00006; 12/13 hand-labelled pivots acceptable, `needs_history` beat the route Choice. Not philippdubach/pi-jev-router ([[ideas/builds-agents]]). P07 | | [jev-blindspot](https://github.com/jsk4581/jev-blindspot) (jsk4581) | one Jev call per prompt (`worth_checking` Noul + 5-level risk Score) decides whether to wake a headless Sonnet or Codex run that lists what the prompt left out, in a side panel | `npm install -g jev-blindspot` | 20 · 2026-09-24 | never edits the session; daemon on 127.0.0.1:7461; `--trust` writes the Codex hook trust hash. No accuracy measured. P38 | | [jev-gateway](https://github.com/vinilana/jev-gateway) (vinilana) | local proxy for Codex, Claude Code, OpenCode, Gemini, Devin: each turn a Jev Choice over the agent's tools forces or hints a tool when confident, else passes through | `npm install -g jev-gateway` | 224 · 2026-09-25 | fails open; per-turn overhead `unverified` (our 2026-09-25 sweep note says ~0.5–1 s; the README capture shows only a 712 ms key check). Author's [bench](https://github.com/vinilana/jev-gateway-bench), 120 sessions: bug-fix cheaper for every model; the feature task cost Opus 5 +61% input and +83% time, and GPT-5.6 Luna solved 3/5 vs 5/5 → [[ideas/head-to-head-agents]]. Routes include OpenCode Zen. P08 | | [JCR](https://github.com/NiazMorshed2007/jcr) (NiazMorshed2007) | walks a tree of capability docs: Jev ranks children with a no-match option, keeps paths within 60% of the best; only chosen command docs reach the agent | clone | 20 · 2026-09-20 | author, 80 runs: agent input −85% (Opus 5), −23% (GPT-5.6-Sol); but Sol slower in 19 of 20 scenarios (median 23.2 → 45.4 s); per-run data not committed → [[ideas/head-to-head-agents]]. Bundles ~80 third-party skills without stated licences (our check). P08 | | [HiRoute](https://github.com/higress-group/HiRoute) (Higress group) | local routing engine for long agent runs; optional self-hosted `jev-decider` REST service: Choice picks the branch, optional Score rates the last segment | `pip install .` (decider); core via checksum-verified script | 21 · 2026-09-25 · Apache-2.0 | defaults 0.80 / 0.50 are "not calibrated guarantees" (author); state capped at 24,000 bytes, 2.8 s budget. **Keep the decider on loopback**: it spends your key. No accuracy. P02 | | [codex-context-diet](https://github.com/konstantinosbotonakis/codex-context-diet) | Codex `PostToolUse`: 5 questions per bulky result; stale ones cut to head + note; local Laya option | `codex plugin marketplace add konstantinosbotonakis/codex-context-diet`, then `codex plugin add codex-context-diet@context-diet` | 3 · 2026-09-23 · NOASSERTION | 20 of 65 results cut; ~$0.00003 each. P07 | | [Yoshi](https://github.com/compozy/yoshi) (CompozyOS) | proxy for Claude Code and Codex; Jev picks history to omit | Bun | 25 · 2026-09-18 | **both current trials slower, no validated saving**. P07 | | [Switchloom](https://github.com/instructa/switchloom) (Instructa) | Codex skill routing tasks across models, Jev mode | `cargo install` | 1 · 2026-09-20 | **author advises against**: no Jev gain in two pilots. P02 | | [Hunch](https://github.com/Kelbie/hunch) (Kelbie) | plain-English repo search, diff review rules, GitHub Action | `npx skills add Kelbie/hunch` | 4 · 2026-09-23 | TypeSafe, gateway or local SemIf. Not steven-shoemaker/hunch or carldaws/hunch ([[ideas/sdks-and-replicas]]). P10, P17 | | [Jevify](https://github.com/altryne/jevify) (altryne) | offload bulk judgments; "Jevify this" audits a product | `npx skills add altryne/jevify --skill jevify` | 25 · 2026-09-21 | not ryana/jevify or fidecastro/jevify (PyPI `jevify`, [[ideas/open-replicas]]) | | [Jev Architect](https://github.com/karanb192/jev-architect) (Karan Bansal) | find, design, test decision loops; may say "keep it in code" | `npx skills add` or plugin | 6 · 2026-09-20 | cf. [[ideas/consult]] | | [Augustus](https://github.com/24601/Augustus) (24601) | skill: find placements, build, evaluate and hill-climb decision systems; Jev the default hosted example | `claude plugin marketplace add 24601/Augustus@v0.7.2`, then `claude plugin install augustus@augustus` | 10 · 2026-09-25 | nearest community analogue to [[ideas/consult]]. P42 | | [prompt2jev](https://github.com/sumleo/prompt2jev) (sumleo) | prompt or LLM code → linted `request.json` + script | plugin or `npx skills add` | 3 · 2026-09-21 | P01 | | [clay-jev-people-ranker](https://github.com/promptgtm-shared/clay-jev-people-ranker) (PromptGTM) | Clay filters, Choice + Noul qualify founders | `install_skill.py` | 0 · 2026-09-21 | 577 people in 20.1 s; 490,395 input tokens, author's estimate $0.0206 (= 490,395 × $0.042/Mtok, our arithmetic). P19 | | [SkillRanker](https://github.com/Dicklesworthstone/skillranker) (Dicklesworthstone) | Rust CLI ranking agent skills for the next step from live session context; Claude Code hooks, abstention, offline replay | install script or `cargo install` | 120 · 2026-09-25 · **MIT with an OpenAI/Anthropic rider** (GitHub: NOASSERTION) | a failed hook recommendation falls back quietly. P08 | | [JevRouter](https://github.com/BillionsBobby/JevRouter) (BillionsBobby) | one Choice over models, subagents, skills, MCP tools, CLIs; its code enforces availability, permissions, risk, confirmation | `npx --yes github:BillionsBobby/JevRouter agent start ...` (**unpinned**: runs the default branch) | 222 · 2026-09-21 | Toolathlon comparison vs DeepSeek V4.1 Flash is 10 tasks, author-run. P02, P05 | | [pi-typesafe](https://github.com/DevMortimer/pi-typesafe) (DevMortimer) | Pi: `typesafe_evaluate` tool (1–32 questions), `/typesafe` playground, one client and key store other extensions share | `pi install npm:pi-typesafe` | 46 · 2026-09-24 | tool off until consent; key file owner-only; 32 questions is its cap, not TypeSafe's. P01 | | [jev-use](https://github.com/shitianfang/jev-use) (shitianfang) | Claude Code, Codex, pi: steps needing no text go to Jev, typed escalation back to the LLM | `npx -y jev-use install` | 27 · 2026-09-22 | via Vercel Gateway 2026-09-19: single call p50 223 / p95 364 ms; 12 questions in one call 224 ms vs 12 calls 2,662 ms. P01, P07 | | [dsh-jev-tools](https://github.com/HorusJiang/dsh-jev-tools) (HorusJiang) | DeepSeek Harness: ranks tool-output segments to prune, screens fetched pages for injection, picks a skill, `jev_gate` before "done" | `dsh plugin --profile web add dsh-jev-tools` | 6 · 2026-09-24 | ranks, never thresholds; pruning fails open, the gate fails to `escalate`; author: picking well is unmeasured. Beside buberlo/dsh-jev ([[ideas/tools-guardrails]]). P07, P08, P16 | | [Jevonian](https://github.com/xinyao27/jevonian) (xinyao27) | local proxy: one Jev call picks model and thinking level per turn | `npm install --global jevonian` | 4 · 2026-09-23 · AGPL-3.0 | **flag:** reuses your Claude Pro/Max and ChatGPT sign-ins through a third-party client; author: "at your own risk". P02 | Names only (our check): [pi-jev](https://github.com/TheoOliveira/pi-jev) (TheoOliveira; unscoped npm `pi-jev`; Pi skill suggestions at Noul ≥ 0.65, opt-in routing, guard, compaction, `pi-jev-gate` CLI; `npx pi-jev-gate` outside a pi-jev project fetches another publisher's package); [jev-pruner](https://github.com/tamaratran/jev-pruner) (tamaratran; trims Bash output over 10,000 estimated tokens, one Noul per chunk, original passes through on failure; needs `CLAUDE_CODE_ENABLE_FUNCTION_HOOKS=1`; same author as fast-jev-compaction on [[ideas/repos-agents]]); [jev-dsh-decision](https://github.com/Devin-AXIS/jev-dsh-decision) (Devin-AXIS, no licence; recommends tools, skills or agents in DeepSeek Harness, never runs them; duplicates dsh-jev-tools); [Eval Genius](https://github.com/alexgreensh/eval-genius) (Alex Greenshpun, Apache-2.0; judge-cascade skill that works on exported answers, no live Jev calls). Elsewhere: building-with-jev-skill, ryana/jevify, hermes-jev-skills, fast-jev-compaction, winnow, Canny, pi-warden, jev-codex-router, jev-router, compact-adviser, jev-rules → [[ideas/repos-agents]]. ## Related - [[ideas/tools-and-integrations]] — hub: MCP servers, connectors, key safety, name collisions - [[ideas/tools-guardrails]] — tool-call gates and rule checks - [[ideas/head-to-head-agents]] — router, gateway and skill-picker measurements (jev-gateway, JCR, JevRouter and others); [[ideas/head-to-head]] — jev-use's latency and cost run - [[ideas/repos-agents]], [[ideas/builds-agents]] — agent repos and builds in depth ## Sources Links inline; raw captures (2026-09-23 to 25) in frontmatter. Names-only lines and "our check" notes rest on our 2026-09-25 vetting at source (docs/sweep/2026-09-25-mrjev/partc.md, parta.md) where no capture exists.